Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 19600
    Prev
    Next
    INDEX
    Explanations

    mentions or descriptions of barrels

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of the word "barrel."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    omen
    -0.84
    olulu
    -0.81
    ostics
    -0.78
    gregation
    -0.77
    omething
    -0.76
    ities
    -0.75
    amaru
    -0.74
    perse
    -0.74
    imilar
    -0.70
    criptions
    -0.68
    POSITIVE LOGITS
     barrel
    1.12
     Barrel
    0.80
     lash
    0.79
     muzzle
    0.79
     hump
    0.75
    toe
    0.75
    hog
    0.72
     scorp
    0.72
    horn
    0.67
     cage
    0.67
    Activations Density 0.012%

    No Known Activations